DeepSeek V3 0324, the DeepSeek model in numbers

What you need to know

DeepSeek V3 0324 is a language model from DeepSeek, released on March 24, 2025. That makes it more than a year old: successors may have shipped since. It is an open-weight model: you can host it yourself on infrastructure you control, and 11 API providers listed on models.dev also offer it. It has no declared reasoning mode: it answers directly, without an extra billed thinking step.

We file it under open-weight models (68 models in this category on the site).

Measured performance

Epoch AI publishes 3 results for DeepSeek V3 0324 on our basket's benchmarks: too few to compute a reliable capability index.

• GPQA Diamond (PhD-level science questions): 67.6% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 37.8% — the best tracked model, GPT-5.5 Pro, reaches 100%
• Aider Polyglot (code editing across several languages): 5,510% — the best tracked model, GPT-5, reaches 8,800%

Pricing and budget

DeepSeek V3 0324 costs $0.27 per million input tokens and $1.1 per million output tokens (median of 11 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.008, or $7.6 for 1,000 such tasks.

That is in line with open-weight models, whose median output price is $1.

To estimate your own budget, use the agent cost calculator.

Technical specifications

Its context window reaches 163,840 tokens, roughly 246 pages of text at 500 words per page: enough for a medium-length document. A single answer can run to 163,840 tokens.

It accepts as input: text.

It can call tools (functions, APIs), which makes it a possible foundation for an AI agent.

Who is it for?

Given its category, DeepSeek V3 0324 is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to DeepSeek V3 0324 are:

• GLM-5.3-Flash (Zhipu AI (Z.ai), index 71.9)
• MiniMax-M3 (MiniMax, index 55.5)
• Muse Glimmer 30B (Meta, $1.2 per million output tokens)
• MiniMax-M2.7 (MiniMax, $1.2 per million output tokens)